eval_results.json

{
    "epoch": 0.9872958257713249,
    "eval_logits/chosen": -0.02468078024685383,
    "eval_logits/rejected": 0.17850716412067413,
    "eval_logps/chosen": -147.27601623535156,
    "eval_logps/rejected": -190.00872802734375,
    "eval_loss": 0.6824025511741638,
    "eval_rewards/accuracies": 0.5833333134651184,
    "eval_rewards/chosen": -0.011536384001374245,
    "eval_rewards/margins": 0.022468576207756996,
    "eval_rewards/rejected": -0.03400496393442154,
    "eval_runtime": 5.069,
    "eval_samples": 464,
    "eval_samples_per_second": 91.536,
    "eval_steps_per_second": 2.959
}